| Title | Poisoning Behavioral Malware Clustering |
| Publication Type | Conference Paper |
| Year of Publication | 2014 |
| Authors | Biggio, Battista, Rieck, Konrad, Ariu, Davide, Wressnegger, Christian, Corona, Igino, Giacinto, Giorgio, Roli, Fabio |
| Conference Name | Proceedings of the 2014 Workshop on Artificial Intelligent and Security Workshop |
| Publisher | ACM |
| Conference Location | New York, NY, USA |
| ISBN Number | 978-1-4503-3153-1 |
| Keywords | Adversarial Machine Learning, AI Poisoning, clustering, computer security, Human Behavior, malware detection, pubcrawl, resilience, Resiliency, Scalability, security evaluation, unsupervised learning |
| Abstract | Clustering algorithms have become a popular tool in computer security to analyze the behavior of malware variants, identify novel malware families, and generate signatures for antivirus systems. However, the suitability of clustering algorithms for security-sensitive settings has been recently questioned by showing that they can be significantly compromised if an attacker can exercise some control over the input data. In this paper, we revisit this problem by focusing on behavioral malware clustering approaches, and investigate whether and to what extent an attacker may be able to subvert these approaches through a careful injection of samples with poisoning behavior. To this end, we present a case study on Malheur, an open-source tool for behavioral malware clustering. Our experiments not only demonstrate that this tool is vulnerable to poisoning attacks, but also that it can be significantly compromised even if the attacker can only inject a very small percentage of attacks into the input data. As a remedy, we discuss possible countermeasures and highlight the need for more secure clustering algorithms. |
| URL | http://doi.acm.org/10.1145/2666652.2666666 |
| DOI | 10.1145/2666652.2666666 |
| Citation Key | biggio_poisoning_2014 |
Poisoning Behavioral Malware Clustering